研究人员推出STEC，一个新颖的证据压缩框架，旨在改进开放域多跳问答（QA）系统中最终答案的选择。该框架解决了当多个搜索轨迹产生异构、冗余或冲突信息时选择正确答案的挑战。STEC首先按归一化的答案身份对轨迹进行分组，并将它们转换为候选特定的证据表示。然后，它使用这些表示来比较证据并选择最可靠的最终答案，在四个多跳QA基准测试中表现优于现有方法。 AI
影响 增强了AI驱动的搜索代理在复杂问答任务中的可靠性。
排序理由 该集群包含一篇详细介绍问答系统新框架的研究论文。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2607.10795v1 Announce Type: new Abstract: In open-domain multi-hop question answering (QA), LLM-based search agents offer a promising approach to knowledge-intensive QA by combining retrieval with reasoning. Existing methods mainly improve open-domain multi-hop QA through r…
In open-domain multi-hop question answering (QA), LLM-based search agents offer a promising approach to knowledge-intensive QA by combining retrieval with reasoning. Existing methods mainly improve open-domain multi-hop QA through reasoning paradigms, retrieval interaction, and s…